Hugging Face's logo

rahulbaburajan
/
gpt-neo-robert-burns

Text Generation
Transformers
PyTorch
gpt_neo
Inference Endpoints
Model card Files Community
1
rahulbaburajan commited on
Commit
e7cc5e6
•
1 Parent(s): a30f170

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +184 -0
trainer_state.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.5348279476165771,
3
+ "best_model_checkpoint": "../saved_models_new/gptNEO_author_RB_epochs15_lr5e-05/checkpoint-4000",
4
+ "epoch": 14.934660858743,
5
+ "global_step": 24000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.24,
12
+ "learning_rate": 3.3333333333333335e-05,
13
+ "loss": 1.6896,
14
+ "step": 2000
15
+ },
16
+ {
17
+ "epoch": 1.24,
18
+ "eval_loss": 1.5621881484985352,
19
+ "eval_runtime": 14.0653,
20
+ "eval_samples_per_second": 25.382,
21
+ "eval_steps_per_second": 12.726,
22
+ "step": 2000
23
+ },
24
+ {
25
+ "epoch": 2.49,
26
+ "learning_rate": 4.7630893153281216e-05,
27
+ "loss": 1.3351,
28
+ "step": 4000
29
+ },
30
+ {
31
+ "epoch": 2.49,
32
+ "eval_loss": 1.5348279476165771,
33
+ "eval_runtime": 14.063,
34
+ "eval_samples_per_second": 25.386,
35
+ "eval_steps_per_second": 12.728,
36
+ "step": 4000
37
+ },
38
+ {
39
+ "epoch": 3.73,
40
+ "learning_rate": 4.289267945984364e-05,
41
+ "loss": 1.154,
42
+ "step": 6000
43
+ },
44
+ {
45
+ "epoch": 3.73,
46
+ "eval_loss": 1.5707106590270996,
47
+ "eval_runtime": 14.0614,
48
+ "eval_samples_per_second": 25.389,
49
+ "eval_steps_per_second": 12.73,
50
+ "step": 6000
51
+ },
52
+ {
53
+ "epoch": 4.98,
54
+ "learning_rate": 3.815446576640607e-05,
55
+ "loss": 0.9265,
56
+ "step": 8000
57
+ },
58
+ {
59
+ "epoch": 4.98,
60
+ "eval_loss": 1.6517491340637207,
61
+ "eval_runtime": 14.0589,
62
+ "eval_samples_per_second": 25.393,
63
+ "eval_steps_per_second": 12.732,
64
+ "step": 8000
65
+ },
66
+ {
67
+ "epoch": 6.22,
68
+ "learning_rate": 3.341625207296849e-05,
69
+ "loss": 0.6998,
70
+ "step": 10000
71
+ },
72
+ {
73
+ "epoch": 6.22,
74
+ "eval_loss": 1.8329756259918213,
75
+ "eval_runtime": 14.0588,
76
+ "eval_samples_per_second": 25.393,
77
+ "eval_steps_per_second": 12.732,
78
+ "step": 10000
79
+ },
80
+ {
81
+ "epoch": 7.47,
82
+ "learning_rate": 2.867803837953092e-05,
83
+ "loss": 0.5298,
84
+ "step": 12000
85
+ },
86
+ {
87
+ "epoch": 7.47,
88
+ "eval_loss": 1.9407192468643188,
89
+ "eval_runtime": 14.0594,
90
+ "eval_samples_per_second": 25.392,
91
+ "eval_steps_per_second": 12.732,
92
+ "step": 12000
93
+ },
94
+ {
95
+ "epoch": 8.71,
96
+ "learning_rate": 2.3939824686093343e-05,
97
+ "loss": 0.391,
98
+ "step": 14000
99
+ },
100
+ {
101
+ "epoch": 8.71,
102
+ "eval_loss": 2.0445475578308105,
103
+ "eval_runtime": 14.0538,
104
+ "eval_samples_per_second": 25.402,
105
+ "eval_steps_per_second": 12.737,
106
+ "step": 14000
107
+ },
108
+ {
109
+ "epoch": 9.96,
110
+ "learning_rate": 1.920161099265577e-05,
111
+ "loss": 0.2698,
112
+ "step": 16000
113
+ },
114
+ {
115
+ "epoch": 9.96,
116
+ "eval_loss": 2.14052414894104,
117
+ "eval_runtime": 14.0566,
118
+ "eval_samples_per_second": 25.397,
119
+ "eval_steps_per_second": 12.734,
120
+ "step": 16000
121
+ },
122
+ {
123
+ "epoch": 11.2,
124
+ "learning_rate": 1.4463397299218195e-05,
125
+ "loss": 0.1802,
126
+ "step": 18000
127
+ },
128
+ {
129
+ "epoch": 11.2,
130
+ "eval_loss": 2.2577126026153564,
131
+ "eval_runtime": 14.0589,
132
+ "eval_samples_per_second": 25.393,
133
+ "eval_steps_per_second": 12.732,
134
+ "step": 18000
135
+ },
136
+ {
137
+ "epoch": 12.45,
138
+ "learning_rate": 9.725183605780622e-06,
139
+ "loss": 0.1244,
140
+ "step": 20000
141
+ },
142
+ {
143
+ "epoch": 12.45,
144
+ "eval_loss": 2.3212833404541016,
145
+ "eval_runtime": 14.0654,
146
+ "eval_samples_per_second": 25.381,
147
+ "eval_steps_per_second": 12.726,
148
+ "step": 20000
149
+ },
150
+ {
151
+ "epoch": 13.69,
152
+ "learning_rate": 4.986969912343047e-06,
153
+ "loss": 0.0874,
154
+ "step": 22000
155
+ },
156
+ {
157
+ "epoch": 13.69,
158
+ "eval_loss": 2.3692986965179443,
159
+ "eval_runtime": 14.0588,
160
+ "eval_samples_per_second": 25.393,
161
+ "eval_steps_per_second": 12.732,
162
+ "step": 22000
163
+ },
164
+ {
165
+ "epoch": 14.93,
166
+ "learning_rate": 2.4875621890547267e-07,
167
+ "loss": 0.0666,
168
+ "step": 24000
169
+ },
170
+ {
171
+ "epoch": 14.93,
172
+ "eval_loss": 2.398601531982422,
173
+ "eval_runtime": 14.0655,
174
+ "eval_samples_per_second": 25.381,
175
+ "eval_steps_per_second": 12.726,
176
+ "step": 24000
177
+ }
178
+ ],
179
+ "max_steps": 24105,
180
+ "num_train_epochs": 15,
181
+ "total_flos": 6267141886574592.0,
182
+ "trial_name": null,
183
+ "trial_params": null
184
+ }